© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18385
    Prev
    Next
    INDEX
    Explanations

    Montreal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olon
    -0.07
    é½IJåħ¨
    -0.06
    trin
    -0.06
    entas
    -0.06
    itera
    -0.06
    ysql
    -0.06
    å¸Ĥå§Ķ常å§Ķ
    -0.06
    illis
    -0.06
    воен
    -0.06
    ilies
    -0.06
    POSITIVE LOGITS
     же
    0.06
    olik
    0.06
    apt
    0.06
    romatic
    0.06
    大çļĦ
    0.05
    éĩĮåħĭ
    0.05
    à²Ĥತ
    0.05
    ocus
    0.05
    ista
    0.05
    æ¢Ń
    0.05
    Activations Density 0.004%

    No Known Activations